skills/use-cli-scout/SKILL.md
Web search, page fetch, and GitHub repo exploration via scout CLI.
npx skillsauth add thkt/dotclaude use-cli-scoutInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Run scout <subcommand> --help for options, --json envelope, exit codes, stdin input, and examples. The help output is the authoritative source for the installed version.
| Purpose | Command |
| ------------- | ------------------------------------- |
| Web search | scout search "query" |
| Fetch page | scout fetch <url> |
| Deep research | scout research "topic" |
| Repo tree | scout repo-tree <owner/repo> |
| Repo read | scout repo-read <owner/repo> <path> |
| Repo overview | scout repo-overview <owner/repo> |
| use-cli-scout | Built-in WebFetch / WebSearch | | ---------------------------------- | ---------------------------------- | | Latest docs, release notes | Never; scout preferred | | GitHub repository exploration | Never; scout repo-* preferred | | Deep research with compiled report | Unavailable; use scout research | | Markdown-clean page extraction | WebFetch lacks Markdown conversion |
| Env Var | Required | Purpose |
| -------------- | -------- | ------------------------------------ |
| GEMINI_API_KEY | Yes | scout search / scout research |
| GITHUB_TOKEN | No | Higher rate limit for scout repo-* |
tools
Delegate implementation to codex (coder) via the herdr-agentchat plugin and drive a two-pane conversation to completion.
development
Extract recurring patterns from past closed PRs/issues and the research findings in workspace/research/, verify them against the latest code, and propose them to docs/wiki/ via PR.
development
Create Decision Records (DR) in MADR v4 format with auto-numbering.
development
Detect flaky tests by shaking them — repeated runs under varied order, parallelism, and seed — plus a static smell scan that flags latent flakiness in tests that currently pass. Classify each target as confirmed-flaky, latent-flaky, or stable and fix the root cause without weakening the test. Do NOT use to fix a confirmed single bug (use /fix) or for static-only code review (use /audit).